selene

selene copied to clipboard

Hi, I tried to run seqweaver on .fa input with the following Selene yml: >ops: [analyze] >model: { path: /lustre/home/acct-bmelgn/bmelgn-3/deepsea/models/seqweaver/seqweaver.py, class: Seqweaver, class_args: { n_classes: 217 } } analyze_sequences: !obj:selene_sdk.predict.AnalyzeSequences...

WeiCSong

Early stopping and other parameters for learning rate scheduler

1

#### Reference Issues/PRs Fixes #183 #### What does this implement/fix? Explain your changes. 1. Added support for other parameters for `ReduceLROnPlateau`. The `TrainModel` object has a new argument `scheduler_kwargs` that...

rfriedman22

Dear Selene Developers, Thanks for creating Selene. I'm finding it super helpful for getting into CNNs. I have trained a model with 36 features using Selene, and this model is...

andrewSharo

Support for other schedulers and early stopping

2

I was hoping to use a different learning rate scheduler than the default implementation (reduce by 0.8 after a validation loss plateau with patience of 16 epochs). Unfortunately it seems...

rfriedman22

Hi， How to modify the model for classification not only regression？

Jasonxu0109

Support multi-inputs

1

- Add `SamplesBatch` class - Utilize `SamplesBatch` class #### Reference Issues/PRs Resolves #161 #### What does this implement/fix? Explain your changes. I've added a `SamplesBatch` class, which holds multiple inputs...

arlapin

Support NN models with multiple inputs

2

Additionally to the sequence, we'd like to provide some other input **(of some different size)** to the model. A simple basic example to illustrate: ```python class SimpleConv(nn.Module): def __init__(self): self.conv_net...

sashuIya

Train and evaluate without `evalute_model` initialization in config does not work

4

In previous versions of Selene, we allowed users to automatically train and evaluate in 1 step without having to specify both the `TrainModel` and `EvaluateModel` classes. This functionality has somehow...

kathyxchen

Support for non-classifier models in IntervalSampler and RandomSampler

1

Similar to Issue #59 , expanding the other samplers to include support for regression models and other continuous-value-predicting models would allow users to analyze gene expression data, chromatin accessibility data,...

laueste

MPRA tutorial - testing r2 with CPU not agreeing with GPUs.

1

Thank you for the development of this package, I am able to reproduce the tutorial results for MPRA (test R2) only when using GPUs. `2020-05-25 13:18:22,128 - test r2: 0.9223668070860704`...

ilibarra